Cause and Effect & Validity Flashcards
State the criteria for Cause and Effect
Cause has to precede the effect in time.
Cause and effect must be correlated with each other.
The correlation between cause and effect cannot be explained by another variable.
Manipulating the cause, changes the effect.
State the two types of Validity
Internal validity: did the IV cause the DV?
External validity: relates to how findings can be generalised to the population
State the nine threats to Internal validity
History Maturation Testing Instrumentation Statistical regression Selection bias Experimental mortality Selection-maturation Expectancy
Define the term History
Events that are not part of the treatment.
For example: when testing VO2 max on sedentary subjects, they train outside of the study which effects results.
Define the term Maturation
Events that occur due to the passage of time not due to the manipulation.
Define the term Testing
Effects of more than one test administration.
For example: VO2 max
Define the term Instrumentation
The change in calibration of a measuring tool which in turn effects results.
Define the term Statistical regression
The selection made based on an extreme score prior to the study. During study the previous observation leads to a regression from the norm.
Define the term Selection bias
Non-random selection of participants.
Define the term Experimental mortality
The differential loss of participants, due to withdrawal from the study.
Define the term Selection-maturation interaction
The passage of time, influencing groups differently.
Define the term Expectancy
The experimenters expectancy / anticipation of participants.
State the four threats to External validity
Reactivity to interactive effects of testing
Interaction of selection biases and treatment
Reactivity effects of experimental arrangements
Multiple treatment inteference
Define Reactivity or interactive effects of testing
Pre test which may make participants more sensitive to testing.
For example: VO2 max before experiment
Define Interaction of selection biases and treatment
Treatment may work only on participants which were selected based on specific characteristics
Define Reactivity effects of experimental arrangements
Setting constraints may influence generalisability.
Define Multiple treatment interference
One treatment may influence the next
State the five Controls to Internal validity
Randomisation
Blind set-ups
Reactive effects of testing
Instrumentation
Differential mortality
Define Randomisation
Participants are selected randomly
Can be matched pairs (not groups)
Randomising treatments or counterbalancing
Define Blind-setups
Double blind setup- neither participant nor researcher are aware of experimental procedure
Single-blind: participants unaware of experimental procedure
Placebos
Define Reactive effects of testing as a way of controlling Internal validity
The elimination of a pre-test
Define Instrumentation as a way of controlling Internal validity
The constant checking and calibration of equipment
Define Differential mortality as a way of controlling Internal validity
Keeping hold of participants during experimental procedures
Describe the four ways of controlling External validity
Selecting; participants, treatments, situations and tests to represent a larger population.
Consider the removal of the pre-test
Randomisation
Ecological validity - does the setting reflect the real world?
Define the term True experiment
Where the manipulation of the IV and the participants have been randomly assigned to the different levels of the IV